We introduce Jais and Jais-chat, new state-of-the-art Arabic-centric
foundation and instruction-tuned open generative large language models (LLMs).
The models are based on the GPT-3 decoder-only architecture and are pretrained
on a mixture of Arabic and English texts, including source code in various
programming languages. With 13 billion parameters, they demonstrate better
knowledge and reasoning capabilities in Arabic than any existing open Arabic
and multilingual models by a sizable margin, based on extensive evaluation.
Moreover, the models are competitive in English compared to English-centric
open models of similar size, despite being trained on much less English data.
We provide a detailed description of the training, the tuning, the safety
alignment, and the evaluation of the models. We release two open versions of
the model -- the foundation Jais model, and an instruction-tuned Jais-chat
variant -- with the aim of promoting research on Arabic LLMs. Available at
this https URL

我们介绍了 Jais 和 Jais-chat，这是最新的阿拉伯语中心基于 GPT-3 解码器结构的大规模生成式语言模型，通过对阿拉伯语和英语文本进行预训练来展示出比现有的阿拉伯语和多语言模型更强的知识和推理能力，提供了详细的训练、调优、安全对齐和评估说明，并发布了两个开源版本的模型，旨在推动阿拉伯语语言模型的研究。